R Notebook

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ─────────────────────────────────── tidyverse 1.3.1 ──
✔ ggplot2 3.3.6     ✔ purrr   0.3.4
✔ tibble  3.1.7     ✔ dplyr   1.0.9
✔ tidyr   1.2.0     ✔ stringr 1.4.0
✔ readr   2.1.2     ✔ forcats 0.5.1
── Conflicts ────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(scales)

Attaching package: ‘scales’

The following object is masked from ‘package:purrr’:

    discard

The following object is masked from ‘package:readr’:

    col_factor

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

library(lubridate)

Attaching package: ‘lubridate’

The following objects are masked from ‘package:base’:

    date, intersect, setdiff, union

Covid Tab

#loads in beds and add year column
beds <- read_csv("raw_data/non_covid_raw_data/beds_by_nhs_board_of_treatment_and_specialty.csv") %>% janitor::clean_names()

beds %>% 
mutate(date = yq(quarter),
         year = year(date))

# bed percentage availablity for "all acute"
# Will need to add filter for year based on user input
beds_plotly <- beds %>%
  filter(specialty_name == "All Acute") %>% 
  group_by(quarter, specialty_name) %>%
  summarise(mean_perc_occ = mean(percentage_occupancy)) %>% 
  ggplot(aes(x = quarter, y = mean_perc_occ))+
  geom_line(aes(colour = specialty_name, group = specialty_name))+
  geom_point(size = 0.5)+
  theme(axis.text.x = element_text(angle = 90, hjust = 1))+
  labs(title = "Mean bed availability for all Acute Patients",
       x = "\nYear and Quarter",
       y = "Average Percentage Occupancy")

`summarise()` has grouped output by 'quarter'. You can override using the `.groups` argument.

ggplotly(beds_plotly) %>% config(displayModeBar = FALSE)

NA
NA

Scotland Shapefile

ae_wait_times wrangling

ae_wait_times <- read_csv("raw_data/non_covid_raw_data/monthly_ae_waitingtimes_202206.csv") %>% janitor::clean_names()

Rows: 15837 Columns: 25── Column specification ──────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (13): Country, HBT, TreatmentLocation, DepartmentType, NumberOfAttendancesEpisodeQF, N...
dbl (12): Month, NumberOfAttendancesAggregate, NumberOfAttendancesEpisode, NumberMeetingTa...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

#glimpse(ae_wait_times)


#make a date and year column with the first date of every month
ae_wait_times <- ae_wait_times %>% 
  mutate(date = ym(month), .after = month,
         year = year(date))

#make a percent column with percent of patients meeting the 4hr target time
ae_wait_times <- ae_wait_times %>% 
  mutate(percent_4hr_target_achieved = (number_meeting_target_aggregate/number_of_attendances_aggregate)*100)

target_2007 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2007) %>% 
  rename(ae_target_2007 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2007)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2008 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2008) %>% 
  rename(ae_target_2008 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2008)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2009 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2009) %>% 
  rename(ae_target_2009 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2009)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2010 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2010) %>% 
  rename(ae_target_2010 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2010)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2011 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2011) %>% 
  rename(ae_target_2011 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2011)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2012 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2012) %>% 
  rename(ae_target_2012 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2012)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2013 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2013) %>% 
  rename(ae_target_2013 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2013)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2014 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2014) %>% 
  rename(ae_target_2014 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2014)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2015 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2015) %>% 
  rename(ae_target_2015 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2015)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2016 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2016) %>% 
  rename(ae_target_2016 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2016)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2017 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2017) %>% 
  rename(ae_target_2017 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2017)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2018 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2018) %>% 
  rename(ae_target_2018 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2018)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2019 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2019) %>% 
  rename(ae_target_2019 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2019)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2020 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2020) %>% 
  rename(ae_target_2020 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2020)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

target_2021 <- ae_wait_times %>%
  group_by(year, hbt) %>% 
  summarise(ae_4hr_target_achieved = mean(percent_4hr_target_achieved, na.rm = TRUE)) %>% 
  filter(year == 2021) %>% 
  rename(ae_target_2021 = ae_4hr_target_achieved) %>% 
  ungroup() %>% 
  select(hbt,ae_target_2021)

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

shape file wrangling

scotland <- st_read("../SG_NHS_HealthBoards_2019_shapefile/SG_NHS_HealthBoards_2019.shp")

Reading layer `SG_NHS_HealthBoards_2019' from data source 
  `C:\Users\neilp\Documents\CODECLAN\phs_scotland_group_project\SG_NHS_HealthBoards_2019_shapefile\SG_NHS_HealthBoards_2019.shp' 
  using driver `ESRI Shapefile'
Simple feature collection with 14 features and 4 fields
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: 5512.998 ymin: 530250.8 xmax: 470332 ymax: 1220302
Projected CRS: OSGB 1936 / British National Grid

# make a smaller version for performance issues
scotland_smaller <- scotland %>% 
  st_simplify(TRUE, dTolerance = 2000)
#fixes problems caused by above 
scotland_smaller <- sf::st_cast(scotland_smaller, "MULTIPOLYGON")

#add in the A&E 4 hr target data for each year
scotland_smaller <-  scotland_smaller %>% 
  mutate(centres = st_centroid(st_make_valid(geometry))) %>%
    mutate(lat = st_coordinates(centres)[,1],
           long = st_coordinates(centres)[,2],
           target_2007 = target_2007$ae_target_2007,
           target_2008 = target_2008$ae_target_2008,
           target_2009 = target_2009$ae_target_2009,
           target_2010 = target_2010$ae_target_2010,
           target_2011 = target_2011$ae_target_2011,
           target_2012 = target_2012$ae_target_2012,
           target_2013 = target_2013$ae_target_2013,
           target_2014 = target_2014$ae_target_2014,
           target_2015 = target_2015$ae_target_2015,
           target_2016 = target_2016$ae_target_2016,
           target_2017 = target_2017$ae_target_2017,
           target_2018 = target_2018$ae_target_2018,
           target_2019 = target_2019$ae_target_2019,
           target_2020 = target_2020$ae_target_2020,
           target_2021 = target_2021$ae_target_2021
                  )


# This will require filtered by the year selected in the dashboard
# Can we get the button or dropdown to pass eg "target_2016" to this in 2 places?
p <- ggplot(scotland_smaller) + 
  geom_sf(aes(fill = target_2021, 
              text = paste("<b>", HBName, "</b>\n", round(target_2021, digits = 2),"%", sep = ""))) + 
  scale_fill_viridis_c(option = "plasma", name = "4Hr A&E Target %")+
  theme_void()+
  labs(title = "Percent of A&E depts making the 4hr target")

Warning: Ignoring unknown aesthetics: text

p %>%
  ggplotly(tooltip = "text") %>%
  style(hoverlabel = list(bgcolor = "white"), hoveron = "fill")%>% 
  config(displayModeBar = FALSE)

SIMD graph

simd <- read_csv("raw_data/non_covid_raw_data/inpatient_and_daycase_by_nhs_board_of_treatment_and_simd.csv") %>% janitor::clean_names()

# average episodes by SIMD value
# currently unfiltered for health board or admission type etc
simd_plotly <- simd %>% 
  drop_na(simd) %>%
  mutate(simd = as.factor(simd)) %>% # gives each simd a separate colour
  group_by(quarter, simd) %>% 
  summarise(avg_episodes = mean(episodes, na.rm = TRUE)) %>% 
  ggplot(aes(x = quarter, y = avg_episodes, group = simd))+
  geom_line(aes(colour = simd))+
  geom_point(size = 0.5)+
  scale_y_continuous(labels = scales::comma)+
  labs(title = "Average Hospital Episodes by SIMD Deprevation score\n",
       x = "\nYear and Quarter",
       y = "Average Episodes\n")+
  theme_minimal()+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

`summarise()` has grouped output by 'quarter'. You can override using the `.groups` argument.

ggplotly(simd_plotly)

Age Graph

age_sex <- read_csv("raw_data/non_covid_raw_data/inpatient_and_daycase_by_nhs_board_of_treatment_age_and_sex.csv") %>% janitor::clean_names()


 # age_sex <-  age_sex %>% 
 #    mutate(quarter = yq(quarter))

# Average number of episode for age groups
# currently unfiltered by department or anything else
age_plotly <- age_sex %>% 
  group_by(quarter, age) %>% 
  summarise(avg_episodes = mean(episodes, na.rm = TRUE)) %>% 
  ggplot(aes(x = quarter, y = avg_episodes))+
  geom_line(aes(colour = age, group = age))+ 
  geom_point(size = 0.5)+
  labs(title = "Average Hospital Episodes by Age Groups\n",
       x = "\nYear and Quarter",
       y = "Average Episodes\n")+
  theme_minimal()+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

`summarise()` has grouped output by 'quarter'. You can override using the `.groups` argument.

  
ggplotly(age_plotly)

Gender

sex_plotly <- age_sex %>% 
  group_by(quarter, sex) %>% 
  summarise(avg_length_of_episode = mean(average_length_of_episode, na.rm = TRUE)) %>% 
  ggplot(aes(x = quarter, y = avg_length_of_episode))+
  geom_line(aes(colour = sex, group = sex))+
  #geom_smooth(aes(colour = sex, group = sex), se = FALSE)+
  geom_point(size = 0.5)+
  labs(title = "Average Hospital Episodes by Gender\n",
       x = "\nYear and Quarter",
       y = "Average Episodes\n")+
  theme_minimal()+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

`summarise()` has grouped output by 'quarter'. You can override using the `.groups` argument.

ggplotly(sex_plotly)